How to Use the Langfuse (LLM Tracing & Evals) MCP in LlamaIndex

Q: Can I use Langfuse (LLM Tracing & Evals) to track LlamaIndex query performance?

Yes. Use getdailymetrics to monitor latency and cost. You can even index these metrics to see if your LlamaIndex retrieval strategy correlates with higher costs.

Q: How do I fetch specific trace details for LlamaIndex?

Call gettrace with a specific ID. The server returns the full telemetry graph, which you can then parse or store in your LlamaIndex knowledge base.

Index your LlamaIndex RAG knowledge base with the Langfuse (LLM Tracing & Evals) MCP Server. Ground your answers in real telemetry data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Langfuse (LLM Tracing & Evals) MCP to LlamaIndex

Create your Vinkius account to connect Langfuse (LLM Tracing & Evals) to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Langfuse (LLM Tracing & Evals) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index trace data for LlamaIndex RAG

Convert your raw telemetry into searchable knowledge. By using `list_traces`, you pull historical logs into your LlamaIndex vector store for semantic search. Your RAG application can then query past performance data. This allows your agent to answer questions about why a query failed based on previous `get_observation` results.

Audit evaluation scores in LlamaIndex

Use `list_scores` to retrieve quality metrics and index them alongside your documents. This lets your agent perform RAG over your own evaluation history. It helps the system understand which document chunks lead to high-quality responses. You simply feed the scores into your index and let the engine retrieve the best context.

Retrieve LlamaIndex prompt templates

Fetch your active prompt templates using `list_prompts`. Your LlamaIndex pipeline can dynamically retrieve the latest prompt version to ensure your retrieval logic stays current. This keeps your application logic separated from your prompt engineering. The agent pulls the specific version it needs right when it prepares the retrieval context.

Setup guide

Set up Langfuse (LLM Tracing & Evals) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Langfuse (LLM Tracing & Evals) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Langfuse (LLM Tracing & Evals) tools.",
)
response = await agent.run("List recent Langfuse (LLM Tracing & Evals) data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Langfuse. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Langfuse (LLM Tracing & Evals) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Langfuse (LLM Tracing & Evals) MCP in LlamaIndex

Use the MCP tools to pull trace data into your LlamaIndex index. By indexing your past observations, your agent can reference previous successful retrieval patterns.

Yes. Use `get_daily_metrics` to monitor latency and cost. You can even index these metrics to see if your LlamaIndex retrieval strategy correlates with higher costs.

Your telemetry data is isolated within the Vinkius sandbox. We use strict token-based authentication to ensure only your LlamaIndex agent can interact with your Langfuse logs.

Call `get_trace` with a specific ID. The server returns the full telemetry graph, which you can then parse or store in your LlamaIndex knowledge base.

The server accesses trace IDs, observation logs, prompt templates, and evaluation scores. It does not store raw user documents, only the metadata related to your LLM interactions.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript